Search Results for author: Yi Wang

Found 209 papers, 87 papers with code

Chinese Grammatical Error Correction Based on Hybrid Models with Data Augmentation

no code implementations AACL (NLP-TEA) 2020 Yi Wang, Ruibin Yuan, Yan‘gen Luo, Yufang Qin, NianYong Zhu, Peng Cheng, Lihuan Wang

A better Chinese Grammatical Error Diagnosis (CGED) system for automatic Grammatical Error Correction (GEC) can benefit foreign Chinese learners and lower Chinese learning barriers.

Data Augmentation Grammatical Error Correction

DoTAT: A Domain-oriented Text Annotation Tool

1 code implementation ACL 2022 Yupian Lin, Tong Ruan, Ming Liang, Tingting Cai, Wen Du, Yi Wang

Secondly, the tool provides annotation of events, nested event and nested entity, which are frequently required in domain-related text structuring tasks.

text annotation

AOCIL: Exemplar-free Analytic Online Class Incremental Learning with Low Time and Resource Consumption

no code implementations23 Mar 2024 Huiping Zhuang, Yuchen Liu, Run He, Kai Tong, Ziqian Zeng, Cen Chen, Yi Wang, Lap-Pui Chau

Online Class Incremental Learning (OCIL) aims to train the model in a task-by-task manner, where data arrive in mini-batches at a time while previous data are not accessible.

Class Incremental Learning Incremental Learning

InternVideo2: Scaling Video Foundation Models for Multimodal Video Understanding

1 code implementation22 Mar 2024 Yi Wang, Kunchang Li, Xinhao Li, Jiashuo Yu, Yinan He, Guo Chen, Baoqi Pei, Rongkun Zheng, Jilan Xu, Zun Wang, Yansong Shi, Tianxiang Jiang, Songze Li, Hongjie Zhang, Yifei HUANG, Yu Qiao, Yali Wang, LiMin Wang

We introduce InternVideo2, a new video foundation model (ViFM) that achieves the state-of-the-art performance in action recognition, video-text tasks, and video-centric dialogue.

 Ranked #1 on Audio Classification on ESC-50 (using extra training data)

Action Classification Action Recognition +12

Recurrent Drafter for Fast Speculative Decoding in Large Language Models

no code implementations14 Mar 2024 Aonan Zhang, Chong Wang, Yi Wang, Xuanyu Zhang, Yunfei Cheng

In this paper, we introduce an improved approach of speculative decoding aimed at enhancing the efficiency of serving large language models.

VideoMamba: State Space Model for Efficient Video Understanding

3 code implementations11 Mar 2024 Kunchang Li, Xinhao Li, Yi Wang, Yinan He, Yali Wang, LiMin Wang, Yu Qiao

Addressing the dual challenges of local redundancy and global dependencies in video understanding, this work innovatively adapts the Mamba to the video domain.

Video Understanding

Non-Intrusive Load Monitoring in Smart Grids: A Comprehensive Review

no code implementations11 Mar 2024 Yinyan Liu, Yi Wang, Jin Ma

Non-Intrusive Load Monitoring (NILM) is pivotal in today's energy landscape, offering vital solutions for energy conservation and efficient management.

Management Non-Intrusive Load Monitoring

Learning to Maximize Mutual Information for Chain-of-Thought Distillation

no code implementations5 Mar 2024 Xin Chen, Hanxian Huang, Yanjun Gao, Yi Wang, Jishen Zhao, Ke Ding

Knowledge distillation, the technique of transferring knowledge from large, complex models to smaller ones, marks a pivotal step towards efficient AI deployment.

Knowledge Distillation Language Modelling +1

AIO2: Online Correction of Object Labels for Deep Learning with Incomplete Annotation in Remote Sensing Image Segmentation

1 code implementation3 Mar 2024 Chenying Liu, Conrad M Albrecht, Yi Wang, Qingyu Li, Xiao Xiang Zhu

AIO2 utilizes a mean teacher model to enhance training robustness with noisy labels to both stabilize the training accuracy curve for fitting in ACT and provide pseudo labels for correction in O2C.

Earth Observation Image Segmentation +1

Task Specific Pretraining with Noisy Labels for Remote sensing Image Segmentation

no code implementations25 Feb 2024 Chenying Liu, Conrad Albrecht, Yi Wang, Xiao Xiang Zhu

In this work, we propose to explore the under-exploited potential of noisy labels for segmentation task specific pretraining, and exam its robustness when confronted with mismatched categories and different decoders during fine-tuning.

Image Segmentation Segmentation +1

Multi-modality transrectal ultrasound video classification for identification of clinically significant prostate cancer

1 code implementation14 Feb 2024 Hong Wu, Juan Fu, Hongsheng Ye, Yuming Zhong, Xuebin Zhou, Jianhua Zhou, Yi Wang

With the aim of effectively identifying prostate cancer, we propose a framework for the classification of clinically significant prostate cancer (csPCa) from multi-modality TRUS videos.

Video Classification

Pyramid Attention Network for Medical Image Registration

1 code implementation14 Feb 2024 Zhuoyuan Wang, Haiqiao Wang, Yi Wang

The advent of deep-learning-based registration networks has addressed the time-consuming challenge in traditional iterative methods. However, the potential of current registration networks for comprehensively capturing spatial relationships has not been fully explored, leading to inadequate performance in large-deformation image registration. The pure convolutional neural networks (CNNs) neglect feature enhancement, while current Transformer-based networks are susceptible to information redundancy. To alleviate these issues, we propose a pyramid attention network (PAN) for deformable medical image registration. Specifically, the proposed PAN incorporates a dual-stream pyramid encoder with channel-wise attention to boost the feature representation. Moreover, a multi-head local attention Transformer is introduced as decoder to analyze motion patterns and generate deformation fields. Extensive experiments on two public brain magnetic resonance imaging (MRI) datasets and one abdominal MRI dataset demonstrate that our method achieves favorable registration performance, while outperforming several CNN-based and Transformer-based registration networks. Our code is publicly available at https://github. com/JuliusWang-7/PAN.

Image Registration Medical Image Registration

Rocks Coding, Not Development--A Human-Centric, Experimental Evaluation of LLM-Supported SE Tasks

no code implementations8 Feb 2024 Wei Wang, Huilong Ning, Gaowei Zhang, Libo Liu, Yi Wang

Our study thus provides first-hand insights into using ChatGPT to fulfill software engineering tasks with real-world developers and motivates the need for novel interaction mechanisms that help developers effectively work with large language models to achieve desired outcomes.

Learning the Market: Sentiment-Based Ensemble Trading Agents

no code implementations2 Feb 2024 Andrew Ye, James Xu, Yi Wang, Yifan Yu, Daniel Yan, Ryan Chen, Bosheng Dong, Vipin Chaudhary, Shuai Xu

We propose the integration of sentiment analysis and deep-reinforcement learning ensemble algorithms for stock trading, and design a strategy capable of dynamically altering its employed agent given concurrent market sentiment.

Sentiment Analysis

Explaining Time Series via Contrastive and Locally Sparse Perturbations

1 code implementation16 Jan 2024 Zichuan Liu, Yingying Zhang, Tianchun Wang, Zefan Wang, Dongsheng Luo, Mengnan Du, Min Wu, Yi Wang, Chunlin Chen, Lunting Fan, Qingsong Wen

Explaining multivariate time series is a compound challenge, as it requires identifying important locations in the time series and matching complex temporal patterns.

Contrastive Learning counterfactual +1

One for All: Toward Unified Foundation Models for Earth Vision

no code implementations15 Jan 2024 Zhitong Xiong, Yi Wang, Fahong Zhang, Xiao Xiang Zhu

Current remote sensing foundation models typically specialize in a single modality or a specific spatial resolution range, limiting their versatility for downstream datasets.

Seamless and multi-resolution energy forecasting

1 code implementation28 Dec 2023 Chenxi Wang, Pierre Pinson, Yi Wang

The relationship between (i) errors in both time and frequency domains and (ii) operational value of the forecasts is analysed.

Scheduling

Guidelines in Wastewater-based Epidemiology of SARS-CoV-2 with Diagnosis

no code implementations26 Dec 2023 Madiha Fatima, Zhihua Cao, Aichun Huang, Shengyuan Wu, Xinxian Fan, Yi Wang, Liu Jiren, Ziyun Zhu, Qiongrou Ye, Yuan Ma, Joseph K. F Chow, Peng Jia, Yangshou Liu, Yubin Lin, Manjun Ye, Tong Wu, ZHIXUN LI, Cong Cai, Wenhai Zhang, Cheris H. Q. Ding, Yuanzhe Cai, Feijuan Huang

With the global spread and increasing transmission rate of SARS-CoV-2, more and more laboratories and researchers are turning their attention to wastewater-based epidemiology (WBE), hoping it can become an effective tool for large-scale testing and provide more ac-curate predictions of the number of infected individuals.

Epidemiology

Dataset Distillation via Adversarial Prediction Matching

1 code implementation14 Dec 2023 Mingyang Chen, Bo Huang, Junda Lu, Bing Li, Yi Wang, Minhao Cheng, Wei Wang

This ensures the memory efficiency of our method and provides a flexible tradeoff between time and memory budgets, allowing us to distil ImageNet-1K using a minimum of only 6. 5GB of GPU memory.

QuickQuakeBuildings: Post-earthquake SAR-Optical Dataset for Quick Damaged-building Detection

no code implementations11 Dec 2023 Yao Sun, Yi Wang, Michael Eineder

Quick and automated earthquake-damaged building detection from post-event satellite imagery is crucial, yet it is challenging due to the scarcity of training data required to develop robust algorithms.

Anomaly Detection Damaged Building Detection +1

TMT-VIS: Taxonomy-aware Multi-dataset Joint Training for Video Instance Segmentation

1 code implementation NeurIPS 2023 Rongkun Zheng, Lu Qi, Xi Chen, Yi Wang, Kun Wang, Yu Qiao, Hengshuang Zhao

What we possess are numerous isolated filed-specific datasets, thus, it is appealing to jointly train models across the aggregation of datasets to enhance data volume and diversity.

Instance Segmentation Semantic Segmentation +1

Layered 3D Human Generation via Semantic-Aware Diffusion Model

no code implementations10 Dec 2023 Yi Wang, Jian Ma, Ruizhi Shao, Qiao Feng, Yu-Kun Lai, Yebin Liu, Kun Li

To keep the generated clothing consistent with the target text, we propose a semantic-confidence strategy for clothing that can eliminate the non-clothing content generated by the model.

MVBench: A Comprehensive Multi-modal Video Understanding Benchmark

1 code implementation28 Nov 2023 Kunchang Li, Yali Wang, Yinan He, Yizhuo Li, Yi Wang, Yi Liu, Zun Wang, Jilan Xu, Guo Chen, Ping Luo, LiMin Wang, Yu Qiao

With the rapid development of Multi-modal Large Language Models (MLLMs), a number of diagnostic benchmarks have recently emerged to evaluate the comprehension capabilities of these models.

Fairness Multiple-choice +8

Multi-delay arterial spin-labeled perfusion estimation with biophysics simulation and deep learning

no code implementations17 Nov 2023 Renjiu Hu, Qihao Zhang, Pascal Spincemaille, Thanh D. Nguyen, Yi Wang

The trained network was further tested in a synthetic brain ASL image based on vasculature network extracted from magnetic resonance (MR) angiography.

Load Data Valuation in Multi-Energy Systems: An End-to-End Approach

no code implementations16 Nov 2023 Yangze Zhou, Qingsong Wen, Jie Song, Xueyuan Cui, Yi Wang

Accurate load forecasting serves as the foundation for the flexible operation of multi-energy systems (MES).

Data Valuation Load Forecasting

Goal-Oriented Wireless Communication Resource Allocation for Cyber-Physical Systems

no code implementations6 Nov 2023 Cheng Feng, Kedi Zheng, Yi Wang, Kaibin Huang, Qixin Chen

We formulate a bandwidth allocation problem aimed at maximizing the information utility gain of transmitted data brought to CPS operation goals.

Decision Making Distributed Optimization +1

Harvest Video Foundation Models via Efficient Post-Pretraining

1 code implementation30 Oct 2023 Yizhuo Li, Kunchang Li, Yinan He, Yi Wang, Yali Wang, LiMin Wang, Yu Qiao, Ping Luo

Building video-language foundation models is costly and difficult due to the redundant nature of video data and the lack of high-quality video-language datasets.

Question Answering Text Retrieval +2

Feature Guided Masked Autoencoder for Self-supervised Learning in Remote Sensing

1 code implementation28 Oct 2023 Yi Wang, Hugo Hernández Hernández, Conrad M Albrecht, Xiao Xiang Zhu

Self-supervised learning guided by masked image modelling, such as Masked AutoEncoder (MAE), has attracted wide attention for pretraining vision transformers in remote sensing.

Multi-Label Image Classification Self-Supervised Learning

Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlook

5 code implementations16 Oct 2023 Ming Jin, Qingsong Wen, Yuxuan Liang, Chaoli Zhang, Siqiao Xue, Xue Wang, James Zhang, Yi Wang, Haifeng Chen, XiaoLi Li, Shirui Pan, Vincent S. Tseng, Yu Zheng, Lei Chen, Hui Xiong

In this survey, we offer a comprehensive and up-to-date review of large models tailored (or adapted) for time series and spatio-temporal data, spanning four key facets: data types, model categories, model scopes, and application areas/tasks.

Time Series Time Series Analysis

PlotMap: Automated Layout Design for Building Game Worlds

no code implementations26 Sep 2023 Yi Wang, Jieliang Luo, Adam Gaier, Evan Atherton, Hilmar Koch

Concretely, we present a system that leverages Reinforcement Learning (RL) to automatically assign concrete locations on a game map to abstract locations mentioned in a given story (plot facilities), following spatial constraints derived from the story.

Decision Making Layout Design +1

Boosting High Resolution Image Classification with Scaling-up Transformers

1 code implementation26 Sep 2023 Yi Wang

We present a holistic approach for high resolution image classification that won second place in the ICCV/CVPPA2023 Deep Nutrient Deficiency Challenge.

Classification Data Augmentation +2

LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Models

2 code implementations26 Sep 2023 Yaohui Wang, Xinyuan Chen, Xin Ma, Shangchen Zhou, Ziqi Huang, Yi Wang, Ceyuan Yang, Yinan He, Jiashuo Yu, Peiqing Yang, Yuwei Guo, Tianxing Wu, Chenyang Si, Yuming Jiang, Cunjian Chen, Chen Change Loy, Bo Dai, Dahua Lin, Yu Qiao, Ziwei Liu

To this end, we propose LaVie, an integrated video generation framework that operates on cascaded video latent diffusion models, comprising a base T2V model, a temporal interpolation model, and a video super-resolution model.

Text-to-Video Generation Video Generation +1

Bitstream-Corrupted Video Recovery: A Novel Benchmark Dataset and Method

1 code implementation NeurIPS 2023 Tianyi Liu, Kejun Wu, Yi Wang, Wenyang Liu, Kim-Hui Yap, Lap-Pui Chau

The past decade has witnessed great strides in video recovery by specialist technologies, like video inpainting, completion, and error concealment.

Video Inpainting

OccluTrack: Rethinking Awareness of Occlusion for Enhancing Multiple Pedestrian Tracking

no code implementations19 Sep 2023 Jianjun Gao, Yi Wang, Kim-Hui Yap, Kratika Garg, Boon Siew Han

Particularly, the improvements on IDF1, IDSw, AssA, and AssR demonstrate the effectiveness of our OccluTrack on tracking and association performance.

Motion Estimation

Representation Learning for Sequential Volumetric Design Tasks

no code implementations5 Sep 2023 Md Ferdous Alam, Yi Wang, Linh Tran, Chin-Yi Cheng, Jieliang Luo

We develop the preference model by estimating the density of the learned representations whereas we train an autoregressive transformer model for sequential design generation.

Representation Learning

Joint Oscillation Damping and Inertia Provision Service for Converter-Interfaced Generation

no code implementations4 Sep 2023 Cheng Feng, Linbin Huang, Xiuqiang He, Yi Wang, Florian Dörfler, Qixin Chen

To address this gap, this paper defines the joint oscillation damping and inertia provision services at the system level, seeking to encourage converter-interfaced generation to provide enhanced damping and fast frequency response capabilities.

Deep Semantic Model Fusion for Ancient Agricultural Terrace Detection

1 code implementation4 Aug 2023 Yi Wang, Chenying Liu, Arti Tiwari, Micha Silver, Arnon Karnieli, Xiao Xiang Zhu, Conrad M Albrecht

Discovering ancient agricultural terraces in desert regions is important for the monitoring of long-term climate changes on the Earth's surface.

Segmentation Semantic Segmentation

Scaling Data Generation in Vision-and-Language Navigation

1 code implementation ICCV 2023 Zun Wang, Jialu Li, Yicong Hong, Yi Wang, Qi Wu, Mohit Bansal, Stephen Gould, Hao Tan, Yu Qiao

Recent research in language-guided visual navigation has demonstrated a significant demand for the diversity of traversable environments and the quantity of supervision for training generalizable agents.

Imitation Learning Vision and Language Navigation +1

Benchmarks and Custom Package for Electrical Load Forecasting

1 code implementation14 Jul 2023 Zhixian Wang, Qingsong Wen, Chaoli Zhang, Liang Sun, Leandro Von Krannichfeldt, Yi Wang

Based on this, we conducted extensive experiments on load data at different levels, providing a reference for researchers to compare different load forecasting models.

Feature Engineering Load Forecasting +2

SimPLe: Similarity-Aware Propagation Learning for Weakly-Supervised Breast Cancer Segmentation in DCE-MRI

1 code implementation29 Jun 2023 Yuming Zhong, Yi Wang

The network first utilizes the pseudo-masks generated using the extreme points to train itself, by minimizing a contrastive loss, which encourages the network to learn more representative features for cancerous voxels.

Segmentation

Semi-Supervised Learning for hyperspectral images by non parametrically predicting view assignment

no code implementations19 Jun 2023 Shivam Pande, Nassim Ait Ali Braham, Yi Wang, Conrad M Albrecht, Biplab Banerjee, Xiao Xiang Zhu

Recently, to effectively train the deep learning models with minimal labelled samples, the unlabeled samples are also being leveraged in self-supervised and semi-supervised setting.

Pseudo Label

Retrieving-to-Answer: Zero-Shot Video Question Answering with Frozen Large Language Models

no code implementations15 Jun 2023 Junting Pan, Ziyi Lin, Yuying Ge, Xiatian Zhu, Renrui Zhang, Yi Wang, Yu Qiao, Hongsheng Li

Video Question Answering (VideoQA) has been significantly advanced from the scaling of recent Large Language Models (LLMs).

Ranked #3 on Temporal/Casual QA on NExT-QA (using extra training data)

Domain Generalization Retrieval +2

SaDI: A Self-adaptive Decomposed Interpretable Framework for Electric Load Forecasting under Extreme Events

no code implementations14 Jun 2023 Hengbo Liu, Ziqing Ma, Linxiao Yang, Tian Zhou, Rui Xia, Yi Wang, Qingsong Wen, Liang Sun

In this paper, we propose a novel forecasting framework, named Self-adaptive Decomposed Interpretable framework~(SaDI), which ensembles long-term trend, short-term trend, and period modelings to capture temporal characteristics in different components.

Load Forecasting Management

Top-Down Framework for Weakly-supervised Grounded Image Captioning

no code implementations13 Jun 2023 Chen Cai, Suchen Wang, Kim-Hui Yap, Yi Wang

Weakly-supervised grounded image captioning (WSGIC) aims to generate the caption and ground (localize) predicted object words in the input image without using bounding box supervision.

Image Captioning Multi-Label Classification +2

ModeT: Learning Deformable Image Registration via Motion Decomposition Transformer

1 code implementation9 Jun 2023 Haiqiao Wang, Dong Ni, Yi Wang

The Transformer structures have been widely used in computer vision and have recently made an impact in the area of medical image registration.

Image Registration Medical Image Registration

DiffLoad: Uncertainty Quantification in Load Forecasting with Diffusion Model

no code implementations31 May 2023 Zhixian Wang, Qingsong Wen, Chaoli Zhang, Liang Sun, Yi Wang

The uncertainties in load forecasting can be divided into two types: epistemic uncertainty and aleatoric uncertainty.

Decision Making energy management +3

GAMUS: A Geometry-aware Multi-modal Semantic Segmentation Benchmark for Remote Sensing Data

1 code implementation24 May 2023 Zhitong Xiong, Sining Chen, Yi Wang, Lichao Mou, Xiao Xiang Zhu

Towards a fair and comprehensive analysis of existing methods, the proposed benchmark consists of 1) a large-scale dataset including co-registered RGB and nDSM pairs and pixel-wise semantic labels; 2) a comprehensive evaluation and analysis of existing multi-modal fusion strategies for both convolutional and Transformer-based networks on remote sensing data.

Segmentation Semantic Segmentation

VideoLLM: Modeling Video Sequence with Large Language Models

1 code implementation22 May 2023 Guo Chen, Yin-Dong Zheng, Jiahao Wang, Jilan Xu, Yifei HUANG, Junting Pan, Yi Wang, Yali Wang, Yu Qiao, Tong Lu, LiMin Wang

Building upon this insight, we propose a novel framework called VideoLLM that leverages the sequence reasoning capabilities of pre-trained LLMs from natural language processing (NLP) for video sequence understanding.

Video Understanding

InternGPT: Solving Vision-Centric Tasks by Interacting with ChatGPT Beyond Language

2 code implementations9 May 2023 Zhaoyang Liu, Yinan He, Wenhai Wang, Weiyun Wang, Yi Wang, Shoufa Chen, Qinglong Zhang, Zeqiang Lai, Yang Yang, Qingyun Li, Jiashuo Yu, Kunchang Li, Zhe Chen, Xue Yang, Xizhou Zhu, Yali Wang, LiMin Wang, Ping Luo, Jifeng Dai, Yu Qiao

Different from existing interactive systems that rely on pure language, by incorporating pointing instructions, the proposed iGPT significantly improves the efficiency of communication between users and chatbots, as well as the accuracy of chatbots in vision-centric tasks, especially in complicated visual scenarios where the number of objects is greater than 2.

Language Modelling

Physics-based network fine-tuning for robust quantitative susceptibility mapping from high-pass filtered phase

no code implementations5 May 2023 Jinwei Zhang, Alexey Dimov, Chao Li, Hang Zhang, Thanh D. Nguyen, Pascal Spincemaille, Yi Wang

Purpose: To improve the generalization ability of convolutional neural network (CNN) based prediction of quantitative susceptibility mapping (QSM) from high-pass filtered phase (HPFP) image.

SSIM

ScatterFormer: Locally-Invariant Scattering Transformer for Patient-Independent Multispectral Detection of Epileptiform Discharges

1 code implementation26 Apr 2023 Ruizhe Zheng, Jun Li, Yi Wang, Tian Luo, Yuguo Yu

Patient-independent detection of epileptic activities based on visual spectral representation of continuous EEG (cEEG) has been widely used for diagnosing epilepsy.

EEG Seizure Detection

Label-free timing analysis of SiPM-based modularized detectors with physics-constrained deep learning

no code implementations24 Apr 2023 Pengcheng Ai, Le Xiao, Zhi Deng, Yi Wang, Xiangming Sun, Guangming Huang, Dong Wang, Yulei Li, Xinchi Ran

We mathematically demonstrate the existence of the optimal function desired by the method, and give a systematic algorithm for training and calibration of the model.

Maximum Spherical Mean Value (mSMV) Filtering for Whole Brain Quantitative Susceptibility Mapping

1 code implementation22 Apr 2023 Alexandra G. Roberts, Dominick J. Romano, Mert Şişman, Alexey V. Dimov, Pascal Spincemaille, Thanh D. Nguyen, Ilhami Kovanlikaya, Susan A. Gauthier, Yi Wang

To develop a tissue field filtering algorithm, called maximum Spherical Mean Value (mSMV), for reducing shadow artifacts in quantitative susceptibility mapping (QSM) of the brain without requiring brain tissue erosion. Residual background field is a major source of shadow artifacts in QSM.

SSN: Stockwell Scattering Network for SAR Image Change Detection

no code implementations22 Apr 2023 Gong Chen, Yanan Zhao, Yi Wang, Kim-Hui Yap

Recently, synthetic aperture radar (SAR) image change detection has become an interesting yet challenging direction due to the presence of speckle noise.

Change Detection Computational Efficiency

A Byte Sequence is Worth an Image: CNN for File Fragment Classification Using Bit Shift and n-Gram Embeddings

1 code implementation14 Apr 2023 Wenyang Liu, Yi Wang, Kejun Wu, Kim-Hui Yap, Lap-Pui Chau

File fragment classification (FFC) on small chunks of memory is essential in memory forensics and Internet security.

Data Augmentation

mcLARO: Multi-Contrast Learned Acquisition and Reconstruction Optimization for simultaneous quantitative multi-parametric mapping

no code implementations7 Apr 2023 Jinwei Zhang, Thanh D. Nguyen, Eddy Solomon, Chao Li, Qihao Zhang, Jiahao Li, Hang Zhang, Pascal Spincemaille, Yi Wang

Results: The retrospective ablation study showed improved image sharpness of mcLARO compared to the baseline network without multi-contrast sampling pattern optimization or image feature fusion, and negligible bias and narrow 95% limits of agreement on regional T1, T2, T2* and QSM values were obtained by the under-sampled reconstructions compared to the fully sampled reconstruction.

Image Reconstruction

VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking

1 code implementation CVPR 2023 LiMin Wang, Bingkun Huang, Zhiyu Zhao, Zhan Tong, Yinan He, Yi Wang, Yali Wang, Yu Qiao

Finally, we successfully train a video ViT model with a billion parameters, which achieves a new state-of-the-art performance on the datasets of Kinetics (90. 0% on K400 and 89. 9% on K600) and Something-Something (68. 7% on V1 and 77. 0% on V2).

 Ranked #1 on Self-Supervised Action Recognition on UCF101 (using extra training data)

Action Classification Action Recognition In Videos +3

PointPatchMix: Point Cloud Mixing with Patch Scoring

no code implementations12 Mar 2023 Yi Wang, Jiaze Wang, Jinpeng Li, Zixu Zhao, Guangyong Chen, Anfeng Liu, Pheng-Ann Heng

With Point-MAE as our baseline, our model surpasses previous methods by a significant margin, achieving 86. 3% accuracy on ScanObjectNN and 94. 1% accuracy on ModelNet40.

Data Augmentation

Exploring Self-supervised Pre-trained ASR Models For Dysarthric and Elderly Speech Recognition

no code implementations28 Feb 2023 Shujie Hu, Xurong Xie, Zengrui Jin, Mengzhe Geng, Yi Wang, Mingyu Cui, Jiajun Deng, Xunying Liu, Helen Meng

Experiments conducted on the UASpeech dysarthric and DementiaBank Pitt elderly speech corpora suggest TDNN and Conformer ASR systems integrated domain adapted wav2vec2. 0 models consistently outperform the standalone wav2vec2. 0 models by statistically significant WER reductions of 8. 22% and 3. 43% absolute (26. 71% and 15. 88% relative) on the two tasks respectively.

speech-recognition Speech Recognition

Rate-Perception Optimized Preprocessing for Video Coding

no code implementations25 Jan 2023 Chengqian Ma, Zhiqiang Wu, Chunlei Cai, Pengwei Zhang, Yi Wang, Long Zheng, Chao Chen, Quan Zhou

In the past decades, lots of progress have been done in the video compression field including traditional video codec and learning-based video codec.

Image Quality Assessment Video Compression

Learning Open-vocabulary Semantic Segmentation Models From Natural Language Supervision

1 code implementation CVPR 2023 Jilan Xu, Junlin Hou, Yuejie Zhang, Rui Feng, Yi Wang, Yu Qiao, Weidi Xie

The former aims to infer all masked entities in the caption given the group tokens, that enables the model to learn fine-grained alignment between visual groups and text entities.

Open Vocabulary Semantic Segmentation Semantic Segmentation

Boosting Accuracy and Robustness of Student Models via Adaptive Adversarial Distillation

1 code implementation CVPR 2023 Bo Huang, Mingyang Chen, Yi Wang, Junda Lu, Minhao Cheng, Wei Wang

Thus, recent studies concern about adversarial distillation (AD) that aims to inherit not only prediction accuracy but also adversarial robustness of a robust teacher model under the paradigm of robust optimization.

Adversarial Robustness Knowledge Distillation

UniFormerV2: Unlocking the Potential of Image ViTs for Video Understanding

no code implementations ICCV 2023 Kunchang Li, Yali Wang, Yinan He, Yizhuo Li, Yi Wang, LiMin Wang, Yu Qiao

The prolific performances of Vision Transformers (ViTs) in image tasks have prompted research into adapting the image ViTs for video tasks.

Video Understanding

Pixels, Regions, and Objects: Multiple Enhancement for Salient Object Detection

1 code implementation CVPR 2023 Yi Wang, Ruili Wang, Xin Fan, Tianzhu Wang, Xiangjian He

A multi-level hybrid loss is firstly designed to guide the network to learn pixel-level, region-level, and object-level features.

object-detection Object Detection +1

NeuralLift-360: Lifting an In-the-Wild 2D Photo to a 3D Object With 360deg Views

no code implementations CVPR 2023 Dejia Xu, Yifan Jiang, Peihao Wang, Zhiwen Fan, Yi Wang, Zhangyang Wang

In this work, we study the challenging task of lifting a single image to a 3D object and, for the first time, demonstrate the ability to generate a plausible 3D object with 360deg views that corresponds well with the given reference image.

Denoising Depth Estimation

A Survey of Face Recognition

no code implementations26 Dec 2022 Xinyi Wang, Jianteng Peng, Sufang Zhang, Bihui Chen, Yi Wang, Yandong Guo

Recent years witnessed the breakthrough of face recognition with deep convolutional neural networks.

Face Recognition

InternVideo: General Video Foundation Models via Generative and Discriminative Learning

1 code implementation6 Dec 2022 Yi Wang, Kunchang Li, Yizhuo Li, Yinan He, Bingkun Huang, Zhiyu Zhao, Hongjie Zhang, Jilan Xu, Yi Liu, Zun Wang, Sen Xing, Guo Chen, Junting Pan, Jiashuo Yu, Yali Wang, LiMin Wang, Yu Qiao

Specifically, InternVideo efficiently explores masked video modeling and video-language contrastive learning as the pretraining objectives, and selectively coordinates video representations of these two complementary frameworks in a learnable manner to boost various video applications.

 Ranked #1 on Action Recognition on Something-Something V1 (using extra training data)

Action Classification Contrastive Learning +8

NeuralLift-360: Lifting An In-the-wild 2D Photo to A 3D Object with 360° Views

1 code implementation29 Nov 2022 Dejia Xu, Yifan Jiang, Peihao Wang, Zhiwen Fan, Yi Wang, Zhangyang Wang

In this work, we study the challenging task of lifting a single image to a 3D object and, for the first time, demonstrate the ability to generate a plausible 3D object with 360{\deg} views that correspond well with the given reference image.

3D Reconstruction Image to 3D +3

A Particle-based Sparse Gaussian Process Optimizer

no code implementations26 Nov 2022 Chandrajit Bajaj, Omatharv Bharat Vaidya, Yi Wang

Task learning in neural networks typically requires finding a globally optimal minimizer to a loss function objective.

Image Classification

CMC v2: Towards More Accurate COVID-19 Detection with Discriminative Video Priors

no code implementations26 Nov 2022 Junlin Hou, Jilan Xu, Nan Zhang, Yi Wang, Yuejie Zhang, Xiaobo Zhang, Rui Feng

This paper presents our solution for the 2nd COVID-19 Competition, occurring in the framework of the AIMIA Workshop at the European Conference on Computer Vision (ECCV 2022).

COVID-19 Diagnosis Representation Learning

Adjacent Slice Feature Guided 2.5D Network for Pulmonary Nodule Segmentation

no code implementations19 Nov 2022 Xinwei Xue, Gaoyu Wang, Long Ma, Qi Jia, Yi Wang

In this paper, we design an adjacent slice feature fusion model to introduce information from adjacent slices.

Segmentation

UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer

3 code implementations17 Nov 2022 Kunchang Li, Yali Wang, Yinan He, Yizhuo Li, Yi Wang, LiMin Wang, Yu Qiao

UniFormer has successfully alleviated this issue, by unifying convolution and self-attention as a relation aggregator in the transformer format.

Video Understanding

LARO: Learned Acquisition and Reconstruction Optimization to accelerate Quantitative Susceptibility Mapping

1 code implementation1 Nov 2022 Jinwei Zhang, Pascal Spincemaille, Hang Zhang, Thanh D. Nguyen, Chao Li, Jiahao Li, Ilhami Kovanlikaya, Mert R. Sabuncu, Yi Wang

In this paper, we present our new framework, called Learned Acquisition and Reconstruction Optimization (LARO), which aims to accelerate the multi-echo gradient echo (mGRE) pulse sequence for QSM.

Non-Iterative Scribble-Supervised Learning with Pacing Pseudo-Masks for Medical Image Segmentation

1 code implementation20 Oct 2022 Zefan Yang, Di Lin, Dong Ni, Yi Wang

To address these issues, we propose a non-iterative method where a stream of varying (pacing) pseudo-masks teach a network via consistency training, named PacingPseudo.

Image Segmentation Medical Image Segmentation +2

EarthNets: Empowering AI in Earth Observation

no code implementations10 Oct 2022 Zhitong Xiong, Fahong Zhang, Yi Wang, Yilei Shi, Xiao Xiang Zhu

Furthermore, a new platform for Earth observation, termed EarthNets, is released as a means of achieving a fair and consistent evaluation of deep learning methods on remote sensing data.

Earth Observation Scene Understanding +1

Can We Solve 3D Vision Tasks Starting from A 2D Vision Transformer?

2 code implementations15 Sep 2022 Yi Wang, Zhiwen Fan, Tianlong Chen, Hehe Fan, Zhangyang Wang

Vision Transformers (ViTs) have proven to be effective, in solving 2D image understanding tasks by training over large-scale image datasets; and meanwhile as a somehow separate track, in modeling the 3D visual world too such as voxels or point clouds.

Point Cloud Segmentation

A multi view multi stage and multi window framework for pulmonary artery segmentation from CT scans

no code implementations8 Sep 2022 Zeyu Liu, Yi Wang, Jing Wen, Yong Zhang, Hao Yin, Chao Guo, Zhongyu Wang

In addition, in order to improve the segmentation performance, we adopt multi-view and multi-window level method, at the same time we employ a fine-tune strategy to mitigate the impact of inconsistent labeling.

Segmentation

PulseDL-II: A System-on-Chip Neural Network Accelerator for Timing and Energy Extraction of Nuclear Detector Signals

no code implementations2 Sep 2022 Pengcheng Ai, Zhi Deng, Yi Wang, Hui Gong, Xinchi Ran, Zijian Lang

Recent literature reveals that deep learning models, especially one-dimensional convolutional neural networks, are promising when dealing with digital signals from nuclear detectors.

Quantization

Quality-Constant Per-Shot Encoding by Two-Pass Learning-based Rate Factor Prediction

no code implementations23 Aug 2022 Chunlei Cai, Yi Wang, Xiaobo Li, Tianxiao Ye

With the help of first pass predicted RF and corresponding actual quality as feedback, the second pass prediction will be highly accurate.

Parameter Prediction

Self-supervised Learning in Remote Sensing: A Review

2 code implementations27 Jun 2022 Yi Wang, Conrad M Albrecht, Nassim Ait Ali Braham, Lichao Mou, Xiao Xiang Zhu

In deep learning research, self-supervised learning (SSL) has received great attention triggering interest within both the computer vision and remote sensing communities.

Earth Observation Multi-Label Image Classification +1

1st Place Solutions for RxR-Habitat Vision-and-Language Navigation Competition (CVPR 2022)

1 code implementation23 Jun 2022 Dong An, Zun Wang, Yangguang Li, Yi Wang, Yicong Hong, Yan Huang, Liang Wang, Jing Shao

Our model consists of three modules: the candidate waypoints predictor (CWP), the history enhanced planner and the tryout controller.

Data Augmentation Vision and Language Navigation

WOLONet: Wave Outlooker for Efficient and High Fidelity Speech Synthesis

no code implementations20 Jun 2022 Yi Wang, Yi Si

Recently, GAN-based neural vocoders such as Parallel WaveGAN, MelGAN, HiFiGAN, and UnivNet have become popular due to their lightweight and parallel structure, resulting in a real-time synthesized waveform with high fidelity, even on a CPU.

Speech Synthesis Vocal Bursts Intensity Prediction

Monitoring Urban Forests from Auto-Generated Segmentation Maps

no code implementations14 Jun 2022 Conrad M Albrecht, Chenying Liu, Yi Wang, Levente Klein, Xiao Xiang Zhu

We present and evaluate a weakly-supervised methodology to quantify the spatio-temporal distribution of urban forests based on remotely sensed data with close-to-zero human interaction.

Semantic Segmentation

UMSNet: An Universal Multi-sensor Network for Human Activity Recognition

no code implementations24 May 2022 Jialiang Wang, Haotian Wei, Yi Wang, Shu Yang, Chi Li

Human activity recognition (HAR) based on multimodal sensors has become a rapidly growing branch of biometric recognition and artificial intelligence.

Human Activity Recognition Time Series +2

Beam Training and Tracking in MmWave Communication: A Survey

no code implementations20 May 2022 Yi Wang, Zhiqing Wei, Zhiyong Feng

This article provides an overview of the beam training and tracking technologies on mmWave bands and reveals the insights for future research in the 6th Generation (6G) mobile network.

Long-run User Value Optimization in Recommender Systems through Content Creation Modeling

no code implementations25 Apr 2022 Akos Lada, Xiaoxuan Liu, Jens Rischbieth, Yi Wang, Yuwen Zhang

Content recommender systems are generally adept at maximizing immediate user satisfaction but to optimize for the \textit{long-run} user value, we need more statistically sophisticated solutions than off-the-shelf simple recommender algorithms.

BIG-bench Machine Learning Recommendation Systems

Self-supervised Vision Transformers for Joint SAR-optical Representation Learning

2 code implementations11 Apr 2022 Yi Wang, Conrad M Albrecht, Xiao Xiang Zhu

Experimental results employing the BigEarthNet-MM dataset demonstrate the benefits of both, the ViT backbones and the proposed multimodal SSL algorithm DINO-MM.

Data Augmentation Earth Observation +2

A Global Modeling Approach for Load Forecasting in Distribution Networks

no code implementations1 Apr 2022 Miha Grabner, Yi Wang, Qingsong Wen, Boštjan Blažič, Vitomir Štruc

Efficient load forecasting is needed to ensure better observability in the distribution networks, whereas such forecasting is made possible by an increasing number of smart meter installations.

Load Forecasting

TAFNet: A Three-Stream Adaptive Fusion Network for RGB-T Crowd Counting

1 code implementation17 Feb 2022 Haihan Tang, Yi Wang, Lap-Pui Chau

Specifically, TAFNet is divided into one main stream and two auxiliary streams.

Crowd Counting

Graph Neural Networks for Graphs with Heterophily: A Survey

no code implementations14 Feb 2022 Xin Zheng, Yi Wang, Yixin Liu, Ming Li, Miao Zhang, Di Jin, Philip S. Yu, Shirui Pan

In the end, we point out the potential directions to advance and stimulate more future research and applications on heterophilic graph learning with GNNs.

Graph Learning

Robust Anomaly Detection for Time-series Data

no code implementations6 Feb 2022 Min Hu, Yi Wang, Xiaowei Feng, Shengchen Zhou, Zhaoyu Wu, Yuan Qin

The experiments showed that in benchmark datasets RADTD possessed higher accuracy and robustness than recurrence qualification analysis and extreme learning machine autoencoder, respectively, and that RADTD accurately detected the occurrence of tunneling settlement accidents, indicating its remarkable performance in accuracy and robustness.

Anomaly Detection Time Series +1

Recurrent Feature Propagation and Edge Skip-Connections for Automatic Abdominal Organ Segmentation

no code implementations2 Jan 2022 Zefan Yang, Di Lin, Dong Ni, Yi Wang

Automatic segmentation of abdominal organs in computed tomography (CT) images can support radiation therapy and image-guided surgery workflows.

Computed Tomography (CT) Organ Segmentation +2

Make A Long Image Short: Adaptive Token Length for Vision Transformers

no code implementations3 Dec 2021 Yichen Zhu, Yuqin Zhu, Jie Du, Yi Wang, Zhicai Ou, Feifei Feng, Jian Tang

The TLA enables the ReViT to process the image with the minimum sufficient number of tokens during inference.

Action Recognition Image Classification

Training BatchNorm Only in Neural Architecture Search and Beyond

no code implementations1 Dec 2021 Yichen Zhu, Jie Du, Yuqin Zhu, Yi Wang, Zhicai Ou, Feifei Feng, Jian Tang

Critically, there is no effort to understand 1) why training BatchNorm only can find the perform-well architectures with the reduced supernet-training time, and 2) what is the difference between the train-BN-only supernet and the standard-train supernet.

Fairness Neural Architecture Search

Reinforcement Learning of Self Enhancing Camera Image and Signal Processing

1 code implementation15 Nov 2021 Chandrajit Bajaj, Yi Wang, Yunhao Yang

Our \textit{Recursive Self Enhancement Reinforcement Learning}(RSE-RL) model views the identification and correction of artifacts as a recursive self-learning and self-improvement exercise and consists of two major sub-modules: (i) The latent feature sub-space clustering/grouping obtained through variational auto-encoders enabling rapid identification of the correspondence and discrepancy between noisy and clean image patches.

Blocking Data Augmentation +4

Learning Ultrasound Scanning Skills from Human Demonstrations

no code implementations9 Nov 2021 Xutian Deng, Ziwei Lei, Yi Wang, Miao Li

Finally, the robustness of the proposed framework is validated with the experiments on real data from sonographers.

Nonlinear ICA Using Volume-Preserving Transformations

no code implementations ICLR 2022 Xiaojiang Yang, Yi Wang, Jiacheng Sun, Xing Zhang, Shifeng Zhang, Zhenguo Li, Junchi Yan

Nonlinear ICA is a fundamental problem in machine learning, aiming to identify the underlying independent components (sources) from data which is assumed to be a nonlinear function (mixing function) of these sources.

Image Synthesis via Semantic Composition

no code implementations ICCV 2021 Yi Wang, Lu Qi, Ying-Cong Chen, Xiangyu Zhang, Jiaya Jia

In this paper, we present a novel approach to synthesize realistic images based on their semantic layouts.

Image Generation Semantic Composition

Conditional Temporal Variational AutoEncoder for Action Video Prediction

no code implementations12 Aug 2021 Xiaogang Xu, Yi Wang, LiWei Wang, Bei Yu, Jiaya Jia

To synthesize a realistic action sequence based on a single human image, it is crucial to model both motion patterns and diversity in the action video.

motion prediction Video Prediction

Open-World Entity Segmentation

2 code implementations29 Jul 2021 Lu Qi, Jason Kuen, Yi Wang, Jiuxiang Gu, Hengshuang Zhao, Zhe Lin, Philip Torr, Jiaya Jia

By removing the need of class label prediction, the models trained for such task can focus more on improving segmentation quality.

Image Manipulation Image Segmentation +2

Weakly-supervised Part-Attention and Mentored Networks for Vehicle Re-Identification

no code implementations17 Jul 2021 Lisha Tang, Yi Wang, Lap-Pui Chau

Current part-level feature learning methods typically detect vehicle parts via uniform division, outside tools, or attention modeling.

Vehicle Re-Identification

Cost-Oriented Load Forecasting

no code implementations5 Jul 2021 Jialun Zhang, Yi Wang, Gabriela Hug

Accurate load prediction is an effective way to reduce power system operation costs.

Load Forecasting

FedNILM: Applying Federated Learning to NILM Applications at the Edge

no code implementations7 Jun 2021 Yu Zhang, Guoming Tang, Qianyi Huang, Yi Wang, Xudong Wang, Jiadong Lou

Non-intrusive load monitoring (NILM) helps disaggregate the household's main electricity consumption to energy usages of individual appliances, thus greatly cutting down the cost in fine-grained household load monitoring.

Federated Learning Model Compression +3

More Behind Your Electricity Bill: a Dual-DNN Approach to Non-Intrusive Load Monitoring

no code implementations1 Jun 2021 Yu Zhang, Guoming Tang, Qianyi Huang, Yi Wang, Hong Xu

Non-intrusive load monitoring (NILM) is a well-known single-channel blind source separation problem that aims to decompose the household energy consumption into itemised energy usage of individual appliances.

blind source separation Non-Intrusive Load Monitoring

Multi-object Tracking with Tracked Object Bounding Box Association

1 code implementation17 May 2021 Nanyang Yang, Yi Wang, Lap-Pui Chau

The CenterTrack tracking algorithm achieves state-of-the-art tracking performance using a simple detection model and single-frame spatial offsets to localize objects and predict their associations in a single network.

Multi-Object Tracking Object

Solve routing problems with a residual edge-graph attention neural network

1 code implementation6 May 2021 Kun Lei, Peng Guo, Yi Wang, Xiao Wu, Wenchao Zhao

In this paper, an end-to-end deep reinforcement learning framework is proposed to solve this type of combinatorial optimization problems.

Combinatorial Optimization Graph Attention +1

Moving Towards Centers: Re-ranking with Attention and Memory for Re-identification

no code implementations4 May 2021 Yunhao Zhou, Yi Wang, Lap-Pui Chau

Specifically, all the feature embeddings of query and gallery images are expanded and enhanced by a linear combination of their neighbors, with the correlation prediction serving as discriminative combination weights.

Re-Ranking Retrieval +1

Motion Artifact Reduction in Quantitative Susceptibility Mapping using Deep Neural Network

no code implementations4 May 2021 Chao Li, Hang Zhang, Jinwei Zhang, Pascal Spincemaille, Thanh D. Nguyen, Yi Wang

An approach to reduce motion artifacts in Quantitative Susceptibility Mapping using deep learning is proposed.

Dense Point Prediction: A Simple Baseline for Crowd Counting and Localization

1 code implementation26 Apr 2021 Yi Wang, Xinyu Hou, Lap-Pui Chau

In this paper, we propose a simple yet effective crowd counting and localization network named SCALNet.

Crowd Counting

Learning Transferable 3D Adversarial Cloaks for Deep Trained Detectors

1 code implementation22 Apr 2021 Arman Maesumi, Mingkang Zhu, Yi Wang, Tianlong Chen, Zhangyang Wang, Chandrajit Bajaj

This paper presents a novel patch-based adversarial attack pipeline that trains adversarial patches on 3D human meshes.

Adversarial Attack Object

Machine-learned 3D Building Vectorization from Satellite Imagery

no code implementations13 Apr 2021 Yi Wang, Stefano Zorzi, Ksenia Bittner

We propose a machine learning based approach for automatic 3D building reconstruction and vectorization.

Generative Adversarial Network Semantic Segmentation

Deep Contrastive Patch-Based Subspace Learning for Camera Image Signal Processing

1 code implementation1 Apr 2021 Yunhao Yang, Yi Wang, Chandrajit Bajaj

Camera Image Signal Processing (ISP) pipelines can get appealing results in different image signal processing tasks.

Contrastive Learning Image Denoising

Temporal Feature Fusion with Sampling Pattern Optimization for Multi-echo Gradient Echo Acquisition and Image Reconstruction

no code implementations10 Mar 2021 Jinwei Zhang, Hang Zhang, Chao Li, Pascal Spincemaille, Mert Sabuncu, Thanh D. Nguyen, Yi Wang

Quantitative imaging in MRI usually involves acquisition and reconstruction of a series of images at multi-echo time points, which possibly requires more scan time and specific reconstruction technique compared to conventional qualitative imaging.

Image Reconstruction

Prevalent Behavior of Smooth Strongly Monotone Discrete-Time Dynamical Systems

no code implementations8 Mar 2021 Yi Wang, Jinxiang Yao, Yufeng Zhang

For C1-smooth strongly monotone discrete-time dynamical systems, it is shown that ``convergence to linearly stable cycles" is a prevalent asymptotic behavior in the measuretheoretic sense.

Dynamical Systems

NeRD: Neural Representation of Distribution for Medical Image Segmentation

1 code implementation6 Mar 2021 Hang Zhang, Rongguang Wang, Jinwei Zhang, Chao Li, Gufeng Yang, Pascal Spincemaille, Thanh Nguyen, Yi Wang

We introduce Neural Representation of Distribution (NeRD) technique, a module for convolutional neural networks (CNNs) that can estimate the feature distribution by optimizing an underlying function mapping image coordinates to the feature distribution.

Image Segmentation Lesion Segmentation +2

A Comprehensive Review of Deep Learning-based Single Image Super-resolution

no code implementations18 Feb 2021 Syed Muhammad Arsalan Bashir, Yi Wang, Mahrukh Khan, Yilong Niu

This survey is an effort to provide a detailed survey of recent progress in single-image super-resolution in the perspective of deep learning while also informing about the initial classical methods used for image super-resolution.

Image Super-Resolution

The Yamabe flow on asymptotically flat manifolds

no code implementations15 Feb 2021 Eric Chen, Yi Wang

We study the Yamabe flow starting from an asymptotically flat manifold $(M^n, g_0)$.

Differential Geometry Analysis of PDEs 53C18, 53Exx

Student Customized Knowledge Distillation: Bridging the Gap Between Student and Teacher

no code implementations ICCV 2021 Yichen Zhu, Yi Wang

We formulate the knowledge distillation as a multi-task learning problem so that the teacher transfers knowledge to the student only if the student can benefit from learning such knowledge.

Image Classification Knowledge Distillation +4

SEGSys: A mapping system for segmentation analysis in energy

no code implementations11 Dec 2020 Xiufeng Liu, Rongling Li, Yi Wang, Per Sieverts Nielsen

This paper showcases the system on the segmentation analysis using an electricity consumption data set and validates the effectiveness of the system.

Databases

Enhance Convolutional Neural Networks with Noise Incentive Block

no code implementations9 Dec 2020 Menghan Xia, Yi Wang, Chu Han, Tien-Tsin Wong

Noise Incentive Block (NIB), which serves as a generic plug-in for any CNN generation model.

Image Generation Translation

RANet: Region Attention Network for Semantic Segmentation

1 code implementation NeurIPS 2020 Dingguo Shen, Yuanfeng Ji, Ping Li, Yi Wang, Di Lin

In contrast to the previous methods, RANet configures the information pathways between the pixels in different regions, enabling the region interaction to exchange the regional context for enhancing all of the pixels in the image.

Object Segmentation +1

Rethinking and Designing a High-performing Automatic License Plate Recognition Approach

no code implementations30 Nov 2020 Yi Wang, Zhen-Peng Bian, Yunhao Zhou, Lap-Pui Chau

Our study illustrates the outstanding design of ALPR with four insights: (1) the resampling-based cascaded framework is beneficial to both speed and accuracy; (2) the highly efficient license plate recognition should abundant additional character segmentation and recurrent neural network (RNN), but adopt a plain convolutional neural network (CNN); (3) in the case of CNN, taking advantage of vertex information on license plates improves the recognition performance; and (4) the weight-sharing character classifier addresses the lack of training images in small-scale datasets.

Data Augmentation License Plate Detection +2

Tongji University Undergraduate Team for the VoxCeleb Speaker Recognition Challenge2020

no code implementations20 Oct 2020 Shufan Shen, Ran Miao, Yi Wang, Zhihua Wei

In this report, we discribe the submission of Tongji University undergraduate team to the CLOSE track of the VoxCeleb Speaker Recognition Challenge (VoxSRC) 2020 at Interspeech 2020.

Data Augmentation Denoising +2

Ensembling Low Precision Models for Binary Biomedical Image Segmentation

no code implementations16 Oct 2020 Tianyu Ma, Hang Zhang, Hanley Ong, Amar Vora, Thanh D. Nguyen, Ajay Gupta, Yi Wang, Mert Sabuncu

Our core idea is straightforward: A diverse ensemble of low precision and high recall models are likely to make different false positive errors (classifying background as foreground in different parts of the image), but the true positives will tend to be consistent.

Image Segmentation Lesion Segmentation +3

Assessing Lesion Segmentation Bias of Neural Networks on Motion Corrupted Brain MRI

no code implementations12 Oct 2020 Tejas Sudharshan Mathai, Yi Wang, Nathan Cross

In this paper, we seek to quantify the bias in terms of the impact that different levels of motion artifacts have on the performance of neural networks engaged in a lesion segmentation task.

Artifact Detection Lesion Segmentation +1

Geometric Loss for Deep Multiple Sclerosis lesion Segmentation

no code implementations29 Sep 2020 Hang Zhang, Jinwei Zhang, Rongguang Wang, Qihao Zhang, Susan A. Gauthier, Pascal Spincemaille, Thanh D. Nguyen, Yi Wang

Multiple sclerosis (MS) lesions occupy a small fraction of the brain volume, and are heterogeneous with regards to shape, size and locations, which poses a great challenge for training deep learning based segmentation models.

Lesion Segmentation Segmentation

Efficient Folded Attention for 3D Medical Image Reconstruction and Segmentation

no code implementations13 Sep 2020 Hang Zhang, Jinwei Zhang, Rongguang Wang, Qihao Zhang, Pascal Spincemaille, Thanh D. Nguyen, Yi Wang

Recently, 3D medical image reconstruction (MIR) and segmentation (MIS) based on deep neural networks have been developed with promising results, and attention mechanism has been further designed to capture global contextual information for performance enhancement.

Computational Efficiency Image Reconstruction +1

Probabilistic Dipole Inversion for Adaptive Quantitative Susceptibility Mapping

no code implementations7 Sep 2020 Jinwei Zhang, Hang Zhang, Mert Sabuncu, Pascal Spincemaille, Thanh Nguyen, Yi Wang

A learning-based posterior distribution estimation method, Probabilistic Dipole Inversion (PDI), is proposed to solve the quantitative susceptibility mapping (QSM) inverse problem in MRI with uncertainty estimation.

Density Estimation

Computer-aided Tumor Diagnosis in Automated Breast Ultrasound using 3D Detection Network

no code implementations31 Jul 2020 Junxiong Yu, Chaoyu Chen, Xin Yang, Yi Wang, Dan Yan, Jianxing Zhang, Dong Ni

The efficacy of our network is verified from a collected dataset of 418 patients with 145 benign tumors and 273 malignant tumors.

Breast Cancer Detection Classification +1

Extending LOUPE for K-space Under-sampling Pattern Optimization in Multi-coil MRI

no code implementations28 Jul 2020 Jinwei Zhang, Hang Zhang, Alan Wang, Qihao Zhang, Mert Sabuncu, Pascal Spincemaille, Thanh D. Nguyen, Yi Wang

The previously established LOUPE (Learning-based Optimization of the Under-sampling Pattern) framework for optimizing the k-space sampling pattern in MRI was extended in three folds: firstly, fully sampled multi-coil k-space data from the scanner, rather than simulated k-space data from magnitude MR images in LOUPE, was retrospectively under-sampled to optimize the under-sampling pattern of in-vivo k-space data; secondly, binary stochastic k-space sampling, rather than approximate stochastic k-space sampling of LOUPE during training, was applied together with a straight-through (ST) estimator to estimate the gradient of the threshold operation in a neural network; thirdly, modified unrolled optimization network, rather than modified U-Net in LOUPE, was used as the reconstruction network in order to reconstruct multi-coil data properly and reduce the dependency on training data.

A Self-Training Approach for Point-Supervised Object Detection and Counting in Crowds

2 code implementations25 Jul 2020 Yi Wang, Junhui Hou, Xinyu Hou, Lap-Pui Chau

In this paper, we propose a novel self-training approach named Crowd-SDNet that enables a typical object detector trained only with point-level annotations (i. e., objects are labeled with points) to estimate both the center points and sizes of crowded objects.

Crowd Counting Object +2

Cache-enabling UAV Communications: Network Deployment and Resource Allocation

no code implementations22 Jul 2020 Tiankui Zhang, Yi Wang, Yuanwei Liu, Wenjun Xu, Arumugam Nallanathan

We formulate a joint optimization problem of UAV deployment, caching placement and user association for maximizing QoE of users, which is evaluated by mean opinion score (MOS).

Can 3D Adversarial Logos Cloak Humans?

1 code implementation25 Jun 2020 Yi Wang, Jingyang Zhou, Tianlong Chen, Sijia Liu, Shiyu Chang, Chandrajit Bajaj, Zhangyang Wang

Contrary to the traditional adversarial patch, this new form of attack is mapped into the 3D object world and back-propagates to the 2D image domain through differentiable rendering.

Object

When Residual Learning Meets Dense Aggregation: Rethinking the Aggregation of Deep Neural Networks

no code implementations19 Apr 2020 Zhiyu Zhu, Zhen-Peng Bian, Junhui Hou, Yi Wang, Lap-Pui Chau

However, the existing networks usually suffer from either redundancy of convolutional layers or insufficient utilization of parameters.

Neural Architecture Search

Attentive Normalization for Conditional Image Generation

1 code implementation CVPR 2020 Yi Wang, Ying-Cong Chen, Xiangyu Zhang, Jian Sun, Jiaya Jia

Traditional convolution-based generative adversarial networks synthesize images based on hierarchical local operations, where long-range dependency relation is implicitly modeled with a Markov chain.

Conditional Image Generation Semantic correspondence +2

VCNet: A Robust Approach to Blind Image Inpainting

2 code implementations ECCV 2020 Yi Wang, Ying-Cong Chen, Xin Tao, Jiaya Jia

Blind inpainting is a task to automatically complete visual contents without specifying masks for missing areas in an image.

Image Inpainting

PointINS: Point-based Instance Segmentation

no code implementations13 Mar 2020 Lu Qi, Yi Wang, Yukang Chen, Yingcong Chen, Xiangyu Zhang, Jian Sun, Jiaya Jia

In this paper, we explore the mask representation in instance segmentation with Point-of-Interest (PoI) features.

Instance Segmentation Object Detection +3

Convolutional Neural Networks with Dynamic Regularization

no code implementations26 Sep 2019 Yi Wang, Zhen-Peng Bian, Junhui Hou, Lap-Pui Chau

That is, the regularization strength is fixed to a predefined schedule, and manual adjustments are required to adapt to various network architectures.

Bridging Commonsense Reasoning and Probabilistic Planning via a Probabilistic Action Language

no code implementations31 Jul 2019 Yi Wang, Shiqi Zhang, Joohyung Lee

In this paper, we present a unified framework to integrate icorpp's reasoning and planning components.

Decision Making

Deep Attentive Features for Prostate Segmentation in 3D Transrectal Ultrasound

1 code implementation3 Jul 2019 Yi Wang, Haoran Dou, Xiao-Wei Hu, Lei Zhu, Xin Yang, Ming Xu, Jing Qin, Pheng-Ann Heng, Tianfu Wang, Dong Ni

Our attention module utilizes the attention mechanism to selectively leverage the multilevel features integrated from different layers to refine the features at each individual layer, suppressing the non-prostate noise at shallow layers of the CNN and increasing more prostate details into features at deep layers.

Image Segmentation Medical Image Segmentation +2

Fully Decoupled Neural Network Learning Using Delayed Gradients

1 code implementation21 Jun 2019 Huiping Zhuang, Yi Wang, Qinglai Liu, Shuai Zhang, Zhiping Lin

Training neural networks with back-propagation (BP) requires a sequential passing of activations and gradients, which forces the network modules to work in a synchronous fashion.

Wide-Context Semantic Image Extrapolation

2 code implementations CVPR 2019 Yi Wang, Xin Tao, Xiaoyong Shen, Jiaya Jia

This paper studies the fundamental problem of extrapolating visual context using deep generative models, i. e., extending image borders with plausible structure and details.

Image Inpainting Image Outpainting +1

Elaboration Tolerant Representation of Markov Decision Process via Decision-Theoretic Extension of Probabilistic Action Language pBC+

no code implementations1 Apr 2019 Yi Wang, Joohyung Lee

Alternatively, the semantics of pBC+ can also be defined in terms of Markov Decision Process (MDP), which in turn allows for representing MDP in a succinct and elaboration tolerant way as well as to leverage an MDP solver to compute pBC+.

Understanding and Comparing Scalable Gaussian Process Regression for Big Data

no code implementations3 Nov 2018 Haitao Liu, Jianfei Cai, Yew-Soon Ong, Yi Wang

This paper devotes to investigating the methodological characteristics and performance of representative global and local scalable GPs including sparse approximations and local aggregations from four main perspectives: scalability, capability, controllability and robustness.

regression

Weight Learning in a Probabilistic Extension of Answer Set Programs

no code implementations14 Aug 2018 Joohyung Lee, Yi Wang

Learning in LPMLN is in accordance with the stable model semantics, thereby it learns parameters for probabilistic extensions of knowledge-rich domains where answer set programming has shown to be useful but limited to the deterministic case, such as reachability analysis and reasoning about actions in dynamic domains.

The conditional permutation test for independence while controlling for confounders

no code implementations14 Jul 2018 Thomas B. Berrett, Yi Wang, Rina Foygel Barber, Richard J. Samworth

Like the conditional randomization test of Cand\`es et al. (2018), our test relies on the availability of an approximation to the distribution of $X \mid Z$.

Methodology Statistics Theory Statistics Theory

Generalized Robust Bayesian Committee Machine for Large-scale Gaussian Process Regression

1 code implementation ICML 2018 Haitao Liu, Jianfei Cai, Yi Wang, Yew-Soon Ong

In order to scale standard Gaussian process (GP) regression to large-scale datasets, aggregation models employ factorized training process and then combine predictions from distributed experts.

Distributed Computing regression

A Probabilistic Extension of Action Language BC+

no code implementations2 May 2018 Joohyung Lee, Yi Wang

We present a probabilistic extension of action language BC+.

Scale-recurrent Network for Deep Image Deblurring

4 code implementations CVPR 2018 Xin Tao, Hongyun Gao, Yi Wang, Xiaoyong Shen, Jue Wang, Jiaya Jia

In single image deblurring, the "coarse-to-fine" scheme, i. e. gradually restoring the sharp image on different resolutions in a pyramid, is very successful in both traditional optimization-based methods and recent neural-network-based approaches.

Ranked #3 on Image Deblurring on GoPro (Params (M) metric, using extra training data)

Deblurring Image Deblurring +1

Online Robust Image Alignment via Subspace Learning From Gradient Orientations

no code implementations ICCV 2017 Qingqing Zheng, Yi Wang, Pheng-Ann Heng

The proposed method integrates the subspace learning, transformed IGO reconstruction and image alignment into a unified online framework, which is robust for aligning images with severe intensity distortions.

Face Recognition

Computing LPMLN Using ASP and MLN Solvers

no code implementations19 Jul 2017 Joohyung Lee, Samidh Talsania, Yi Wang

LPMLN is a recent addition to probabilistic logic programming languages.

Incremental Kernel Null Space Discriminant Analysis for Novelty Detection

no code implementations CVPR 2017 Juncheng Liu, Zhouhui Lian, Yi Wang, Jianguo Xiao

This validates the superiority of our IKNDA against the state of the art in novelty detection for large-scale data.

Novelty Detection

Fine-grained Recurrent Neural Networks for Automatic Prostate Segmentation in Ultrasound Images

no code implementations6 Dec 2016 Xin Yang, Lequan Yu, Lingyun Wu, Yi Wang, Dong Ni, Jing Qin, Pheng-Ann Heng

Additionally, our approach is general and can be extended to other medical image segmentation tasks, where boundary incompleteness is one of the main challenges.

Image Segmentation Medical Image Segmentation +1

On the Semantic Relationship between Probabilistic Soft Logic and Markov Logic

no code implementations28 Jun 2016 Joohyung Lee, Yi Wang

Markov Logic Networks (MLN) and Probabilistic Soft Logic (PSL) are widely applied formalisms in Statistical Relational Learning, an emerging area in Artificial Intelligence that is concerned with combining logical and statistical AI.

Relational Reasoning

Stochastic Patching Process

no code implementations23 May 2016 Xuhui Fan, Bin Li, Yi Wang, Yang Wang, Fang Chen

Due to constraints of partition strategy, existing models may cause unnecessary dissections in sparse regions when fitting data in dense regions.

Hybrid evolutionary algorithm with extreme machine learning fitness function evaluation for two-stage capacitated facility location problem

no code implementations22 May 2016 Peng Guo, Wenming Cheng, Yi Wang

This paper considers the two-stage capacitated facility location problem (TSCFLP) in which products manufactured in plants are delivered to customers via storage depots.

Consistency Analysis of Nearest Subspace Classifier

no code implementations24 Jan 2015 Yi Wang

The Nearest subspace classifier (NSS) finds an estimation of the underlying subspace within each class and assigns data points to the class that corresponds to its nearest subspace.

General Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.